DeepSeek: Deepseek OCR
deepseek/deepseek-ocr
DeepSeek-OCR is a comprehensive Optical Character Recognition (OCR) model that analyzes and understands complex documents. It excels at challenging OCR tasks, including recognizing mathematical formulas and processing text that is curved, rotated, or overlapping.
Model specifications
- Input
- text
- Output
- text
- Context
- 8,200 tokens
- Max output
- 8,200 tokens
- Input price
- $0.3 / 1M tokens
- Output price